© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38028
    Prev
    Next
    INDEX
    Explanations

    users and database joins

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on programming‐language code tokens—especially keywords (public, virtual, JOIN, namespace, etc.), type names, and other syntax elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    telli
    -1.02
    起点
    -0.90
     new
    -0.87
    探索
    -0.86
    陶瓷
    -0.83
    ៀ
    -0.82
     Анти
    -0.80
     GBIF
    -0.79
    Any
    -0.78
    麒麟
    -0.78
    POSITIVE LOGITS
    AspNet
    1.24
     Users
    1.15
    users
    1.06
     ICollection
    0.98
     users
    0.98
    Users
    0.94
    fk
    0.83
     ciudadanos
    0.80
    User
    0.79
    用户
    0.79
    Activations Density 0.015%

    No Known Activations